Action Recognition on UCF101 1 (test)
94.6AccuracyProViCo
Evaluation results
| Method | Links | |
|---|---|---|
| ProViCoType=(ii), Backbone=R3D-50 (31.7M), Input size=224 × 224, Batch size=512, Pretrain data=UCF101, Finetune=true2022.04 | 94.6 | |
| CORPType=(iii), Backbone=R3D-50 (31.7M), Input size=224 × 224, Batch size=512, Pretrain data=UCF/HMDB, Finetune=true2022.04 | 93.5 | |
| CVRLType=(ii), Backbone=R3D-50 (31.7M), Input size=224 × 224, Batch size=1024, Pretrain data=K400, Finetune=true2022.04 | 92.2 | |
| GDTBackbone=R(2+1)D-18, Finetune Input Size=30 x 112^2, Advanced hierarchical sampling=true2022.01 | 90.9 | |
| CORPType=(iii), Backbone=R3D-50 (31.7M), Input size=224 × 224, Batch size=512, Pretrain data=K400, Finetune=false2022.04 | 90.2 | |
| MCNType=(ii), Backbone=R3D-18 (20.2M), Input size=128 × 128, Batch size=80, Pretrain data=K400, Finetune=true, Notes=Additional residual views used2022.04 | 89.7 | |
| RINCEBackbone=R(2+1)D-18, Finetune Input Size=32 x 224^22022.01 | 88.8 | |
| InfoNCEBackbone=R(2+1)D-18, Finetune Input Size=32 x 224^22022.01 | 88.6 | |
| CATEType=(ii), Backbone=R3D-50 (31.7M), Input size=128 × 128, Batch size=1024, Pretrain data=K400, Finetune=true2022.04 | 88.4 | |
| AVID+CMABackbone=R(2+1)D-18, Finetune Input Size=32 x 224^22022.01 | 87.5 | |
| ProViCoType=(ii), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=96, Pretrain data=K400, Finetune=true2022.04 | 87.2 | |
| TECType=(iii), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=192, Pretrain data=K400, Finetune=true2022.04 | 87.1 | |
| Cross-AVIDBackbone=R(2+1)D-18, Finetune Input Size=32 x 224^22022.01 | 86.9 | |
| XDCBackbone=R(2+1)D-18, Finetune Input Size=32 x 224^22022.01 | 86.8 | |
| ProViCoType=(ii), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=96, Pretrain data=UCF101, Finetune=true2022.04 | 86.1 | |
| AVTSBackbone=MC3-18, Finetune Input Size=25 x 224^22022.01 | 85.8 | |
| Robust-xIDBackbone=R(2+1)D-18, Finetune Input Size=32 x 224^22022.01 | 85.6 | |
| ProViCoType=(ii), Backbone=R3D-18 (20.2M), Input size=112 × 112, Batch size=96, Pretrain data=K400, Finetune=true2022.04 | 85.6 | |
| MCNType=(ii), Backbone=R3D-18 (20.2M), Input size=128 × 128, Batch size=80, Pretrain data=UCF/HMDB, Finetune=true2022.04 | 85.4 | |
| TECType=(iii), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=192, Pretrain data=UCF101, Finetune=true2022.04 | 85.2 | |
| CATEType=(ii), Backbone=R3D-50 (31.7M), Input size=224 × 224, Batch size=1024, Pretrain data=K400, Finetune=false2022.04 | 84.3 | |
| TCLRType=(i), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=40, Pretrain data=K400, Finetune=true2022.04 | 84.3 | |
| ProViCoType=(ii), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=96, Pretrain data=K400, Finetune=false2022.04 | 84.1 | |
| ProViCoType=(ii), Backbone=R3D-18 (20.2M), Input size=112 × 112, Batch size=96, Pretrain data=UCF101, Finetune=true2022.04 | 83.7 | |
| SeLaViBackbone=R(2+1)D-18, Finetune Input Size=32 x 112^22022.01 | 83.1 | |
| ProViCoType=(ii), Backbone=R3D-18 (20.2M), Input size=112 × 112, Batch size=96, Pretrain data=K400, Finetune=false2022.04 | 82.9 | |
| TCLRType=(ii), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=40, Pretrain data=UCF101, Finetune=true2022.04 | 82.8 | |
| RTTType=(i), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=256, Pretrain data=UCF101, Finetune=true2022.04 | 81.6 | |
| CBTBackbone=S3D, Finetune Input Size=16 x 112^22022.01 | 79.5 | |
| MFOType=(ii), Backbone=R3D-18 (20.2M), Input size=112 × 112, Batch size=256, Pretrain data=K400, Finetune=true2022.04 | 79.1 | |
| VideoMoCoType=(ii), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Batch size=128, Pretrain data=K400, Finetune=true2022.04 | 78.7 | |
| MFOType=(ii), Backbone=R3D-18 (20.2M), Input size=112 × 112, Batch size=256, Pretrain data=UCF101, Finetune=true2022.04 | 76.2 | |
| DPCBackbone=R3D-18, Finetune Input Size=25 x 128^22022.01 | 75.7 | |
| DSMType=(i), Backbone=I3D (25.0M), Input size=224 × 224, Batch size=128, Pretrain data=K400, Finetune=true2022.04 | 74.8 | |
| ClipOrderBackbone=R3D-18, Finetune Input Size=16 x 112^22022.01 | 72.4 | |
| PRPType=(i), Backbone=R(2+1)D (15.4M), Input size=112 × 112, Pretrain data=UCF101, Finetune=true2022.04 | 72.1 | |
| DSMType=(i), Backbone=C3D (34.8M), Input size=112 × 112, Batch size=128, Pretrain data=UCF101, Finetune=true2022.04 | 70.3 | |
| VCPType=(i), Backbone=C3D (34.8M), Input size=112 × 112, Pretrain data=UCF101, Finetune=true2022.04 | 68.5 | |
| MFOType=(ii), Backbone=R3D-18 (20.2M), Input size=112 × 112, Batch size=256, Pretrain data=K400, Finetune=false2022.04 | 63.2 | |
| 3D-RotNetBackbone=R3D-18, Finetune Input Size=16 x 112^22022.01 | 62.9 | |
| Motion and Appearance Statistics (MAS)Pre-training Dataset=Kinetics2019.04 | 61.2 | |
| ST-puzzlePre-training Dataset=Kinetics2019.04 | 60.6 | |
| Motion and Appearance Statistics (MAS)Pre-training Dataset=UCF1012019.04 | 58.8 | |
| OPNPre-training Dataset=UCF1012019.04 | 56.3 | |
| GeometryPre-training Dataset=UCF1012019.04 | 55.1 | |
| VGANPre-training Dataset=UCF1012019.04 | 52.1 | |
| Seq Ver.Pre-training Dataset=UCF1012019.04 | 50.9 | |
| TempCohPre-training Dataset=UCF1012019.04 | 45.4 | |
| Object PatchPre-training Dataset=UCF1012019.04 | 42.7 | |
| DrLimPre-training Dataset=UCF1012019.04 | 38.4 |